AAAI

Association for the Advancement of Artificial Intelligence

Home > Proceedings / Proceedings of the AAAI Conference on Artificial Intelligence, 36 > No. 11: IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations

Transformation of Emotions in Images Using Poisson Blended Generative Adversarial Networks (Student Abstract)

Authors

Aristidis Dernelakis

Johns Hopkins University Applied Physics Laboratory University of Maryland, Baltimore County


Jungin Kim

Johns Hopkins University Applied Physics Laboratory Johns Hopkins University


Kevin Velasquez

Johns Hopkins University Applied Physics Laboratory Johns Hopkins University


Lee Stearns

Johns Hopkins University Applied Physics Laboratory


Proceedings:

No. 11: IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations

Volume

Issue:

Proceedings of the AAAI Conference on Artificial Intelligence, 36

Track:

AAAI Student Abstract and Poster Program

Downloads:

Download PDF

Abstract:

We propose a novel method for transforming the emotional content in an image to a specified target emotion. Existing techniques such as a single generative adversarial network (GAN) struggle to perform well on unconstrained images, especially when data is limited. Our method addresses this limitation by blending the outputs from two networks to better transform fine details (e.g., faces) while still operating on the broader styles of the full image. We demonstrate our method's potential through a proof-of-concept implementation.

DOI:

10.1609/aaai.v36i11.21603


AAAI

Proceedings of the AAAI Conference on Artificial Intelligence, 36